Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 27-RESID-POST-AA
    6. 60804
    Prev
    Next
    INDEX
    Explanations

    say type

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tracking
    -0.07
    ルド
    -0.06
     Athletics
    -0.06
    iali
    -0.06
     Strong
    -0.06
    ิทย
    -0.06
     CX
    -0.06
     TokenType
    -0.06
     recursos
    -0.06
    Adult
    -0.06
    POSITIVE LOGITS
     Mae
    0.08
    esture
    0.07
    edom
    0.07
     Reggie
    0.07
     penny
    0.06
     Neb
    0.06
    .Generation
    0.06
    -Pack
    0.06
    .getAll
    0.06
    �
    0.06
    Activations Density 0.060%

    No Known Activations